The NLP community has recently witnessed the success of Large Language Models (LLMs) across various Natural Language Processing (NLP) tasks. However, the potential of LLMs for word-level auto-completion in a multilingual context has not been thoroughly explored yet. To address this gap and benchmark the performance of LLMs, we propose an LLM-based system for the WMT23 Word-Level Auto-Completion (WLAC) task. Our system utilizes ChatGPT to represent LLMs and evaluates its performance in three translation directions: Chinese-English, German-English, and English-German. We also study the task under zero-shot and few-shot settings to assess the potential benefits of incorporating exemplars from the training set in guiding the LLM to perform the task. The results of our experiments show that, on average, our system attains a 29.8% accuracy on the test set. Further analyses reveal that LLMs struggle with WLAC in the zero-shot setting, but performance significantly improves with the help of additional exemplars, though some common errors still appear frequently. These findings have important implications for incorporating LLMs into computer-aided translation systems, as they can potentially enhance the quality of translations. Our codes for evaluation are available at https://github.com/ethanyiwu/WLAC.

Pre-trained language models have become a crucial part of ranking systems and achieved very impressive effects recently. To maintain high performance while keeping efficient computations, knowledge distillation is widely used. In this paper, we focus on two key questions in knowledge distillation for ranking models: 1) how to ensemble knowledge from multi-teacher; 2) how to utilize the label information of data in the distillation process. We propose a unified algorithm called Pairwise Iterative Logits Ensemble (PILE) to tackle these two questions simultaneously. PILE ensembles multi-teacher logits supervised by label information in an iterative way and achieved competitive performance in both offline and online experiments. The proposed method has been deployed in a real-world commercial search system.

Domain adaptation assumes that samples from source and target domains are freely accessible during a training phase. However, such assumption is rarely plausible in the real-world and may causes data-privacy issues, especially when the label of the source domain can be a sensitive attribute as an identifier. SemEval-2021 task 10 focuses on these issues. We participate in the task and propose novel frameworks based on self-training method. In our systems, two different frameworks are designed to solve text classification and sequence labeling. These approaches are tested to be effective which ranks the third among all system in subtask A, and ranks the first among all system in subtask B.

Unsupervised extractive document summarization aims to select important sentences from a document without using labeled summaries during training. Existing methods are mostly graph-based with sentences as nodes and edge weights measured by sentence similarities. In this work, we find that transformer attentions can be used to rank sentences for unsupervised extractive summarization. Specifically, we first pre-train a hierarchical transformer model using unlabeled documents only. Then we propose a method to rank sentences using sentence-level self-attentions and pre-training objectives. Experiments on CNN/DailyMail and New York Times datasets show our model achieves state-of-the-art performance on unsupervised summarization. We also find in experiments that our model is less dependent on sentence positions. When using a linear combination of our model and a recent unsupervised model explicitly modeling sentence positions, we obtain even better results.

Adversarial training is a mean of regularizing classification algorithms by generating adversarial noise to the training data. We apply adversarial training in relation extraction within the multi-instance multi-label learning framework. We evaluate various neural network architectures on two different datasets. Experimental results demonstrate that adversarial training is generally effective for both CNN and RNN models and significantly improves the precision of predicted relations.

We introduce improved guidelines for annotation of sentence specificity, addressing the issues encountered in prior work. Our annotation provides judgements of sentences in context. Rather than binary judgements, we introduce a specificity scale which accommodates nuanced judgements. Our augmented annotation procedure also allows us to define where in the discourse context the lack of specificity can be resolved. In addition, the cause of the underspecification is annotated in the form of free text questions. We present results from a pilot annotation with this new scheme and demonstrate good inter-annotator agreement. We found that the lack of specificity distributes evenly among immediate prior context, long distance prior context and no prior context. We find that missing details that are not resolved in the the prior context are more likely to trigger questions about the reason behind events, “why” and “how”. Our data is accessible at http://www.cis.upenn.edu/~nlp/corpora/lrec16spec.html